A federated learning method that communicates only adapters and prototypes achieves accuracy close to the best adapter-only baseline while offering prototype-based visual explanations.
In Proceed- ings of the IEEE/CVF international conference on computer vision, 15076–15086 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
A federated learning method that communicates only adapters and prototypes achieves accuracy close to the best adapter-only baseline while offering prototype-based visual explanations.